[论文] MetaPerch: Learning from metadata for bioacoustics foundation models

论文概要

研究领域: ML 作者: Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer 发布时间: 2026-07-15 arXiv: 2607.14072

中文摘要

生物声学基础模型依赖大规模公民科学平台如Xeno-Canto获取地理和生态多样化数据。近期研究表明，仅监督就能在这种大规模数据上训练时产生最先进的物种检测模型——然而，这些社区驱动数据中心中随时可用的记录元数据仍有未利用的潜力。在本工作中，我们探索使用元数据——如位置和时间——作为辅助监督信号，允许模型在其学习表示中利用物种-元数据相关性。辅助元数据损失提供超越单独发声的额外信息，可鼓励更丰富、更稳健的表示，更好地泛化到物种分布和声学域偏移——这对真实世界被动声学监测（PAM）部署中的重要挑战。我们引入MetaPerch，一种在多个挑战性域上实现强物种识别性能的新基础模型，并对17个生物声学数据集上9种多样化元数据源的影响进行广泛实证研究。

原文摘要

Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata -- such as location and time -- as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution an...

--- *自动采集于 2026-07-17*

#论文 #arXiv #ML #小凯